Commodity information pushing method and device, electronic equipment and readable storage medium
By sending product information to users and generating tags based on feedback information, the problem of inaccurate user push information in the existing technology is solved, fast and accurate push of user information is achieved, user needs are deeply developed, and user transaction rate and loyalty are improved. .
Patent Information
- Application Number
- CN202410988066.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-23
- Publication Date
- 2024-11-12
AI Technical Summary
The prior art is time-consuming and labor-intensive to obtain user browsing data, and cannot deeply develop user needs, resulting in inaccurate information being pushed by users.
By sending product information to users and generating tags based on feedback information, determining the target user group, and then pushing corresponding information, reducing dependence on browsing data and improving the comprehensiveness and accuracy of tags.
It realizes the rapid and accurate push of information, reduces the cost of users pushing information, and can deeply develop user needs and improve user transaction rates and loyalty.
Smart Images

Figure CN118941363A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data information processing technology, and in particular to a method, device, electronic device and readable storage medium for pushing commodity information. Background Art
[0002] 4S stores are increasingly paying attention to the care of existing car owners and user operations. The reasons behind this can be summarized as follows: 1. Market changes and competitive pressure: As the automobile market gradually becomes saturated, the growth rate of new car sales slows down, and 4S stores face greater market competition pressure. In such a market environment, maintaining old users, improving user loyalty and promoting old users' repurchase have become important means to improve performance. 2. Improvement of user value awareness: Car owners are not only a stable source of income for 4S stores, but also an important disseminator of brand reputation and image. By caring for existing car owners and providing high-quality services, user satisfaction can be improved, and then brand loyalty can be enhanced, forming a word-of-mouth effect and attracting more new users. 3. The importance of customer relationship management (CRM): In the current market environment, CRM plays an increasingly important role in the operation of 4S stores. By establishing a complete CRM system and conducting refined management of existing car owners, it is possible to better understand user needs, provide personalized services, and improve user satisfaction and loyalty. 4. The severity of user churn: User churn is one of the important problems facing 4S stores. Lack of effective user care and service can easily lead to user loss to competitors. Therefore, by strengthening the care and operation of existing car owners, the user churn rate can be effectively reduced and user stickiness can be improved. 5. The importance of after-sales service: After-sales service is an important link for 4S stores to establish long-term relationships with existing car owners. Providing high-quality after-sales service can solve the problems encountered by users during the use of the vehicle and enhance users' trust and loyalty to the brand. 6. Changes in marketing strategies: With the changes in the market, the marketing strategies of 4S stores are also gradually changing. From the past focus on new car sales to the current focus on the care and operation of existing car owners, it reflects the diversification and personalization of marketing strategies. In summary, automobile 4S stores are paying more and more attention to the care and user operation issues of existing car owners, mainly based on market changes, the improvement of user value awareness, the importance of CRM, the severity of user churn, the importance of after-sales service, and the change of marketing strategies. By strengthening the care and operation of existing car owners, 4S stores can establish more stable user relationships and enhance brand image and performance.
[0003] However, the current conventional practice is to obtain the user's browsing data, label the user according to the user's browsing data, and then send different product information according to users with different labels. This method has the following two problems. First, it is necessary to find the browsing data of "user A" from a large number of websites and software, which is time-consuming and laborious. Second, it is impossible to effectively develop the needs of user A. For example, although "user A" has not browsed "model A", it does not mean that "user A" does not like "model A". It may be that the user has not thought of it. Therefore, this method cannot deeply develop the needs of user A.
[0004] Therefore, inventing a method for pushing product information that can deeply explore user needs is a technical problem that needs to be solved urgently. Summary of the invention
[0005] The present invention aims to solve or improve the problem in the related art that labeling users based on searching for their browsing data is time-consuming and labor-intensive.
[0006] A first aspect of the present invention provides a method for pushing commodity information.
[0007] A second aspect of the present invention provides a device for pushing commodity information.
[0008] A third aspect of the present invention provides an electronic device.
[0009] A fourth aspect of the present invention provides a readable storage medium.
[0010] The present invention provides a method for pushing product information, including: determining multiple push objects; pushing at least one first product information to each push object; obtaining feedback information of each push object for the first product information; generating a label corresponding to the push object based on the feedback information of each push object for the first product information; receiving second product information; determining a target push object based on the second product information and the label of the push object; and pushing the second product information to the target push object.
[0011] The method for pushing commodity information provided by the present invention first determines multiple push objects, which are users, and pushes at least one first commodity information to each push object. The first commodity information can be an article that has been published, etc., and feedback information of each push object for the first commodity information is obtained. In this way, a label of the corresponding push object can be generated based on the feedback information of each push object for the first commodity information. For example, if the feedback effect of "push object A" on "article A" is good, then the keywords in "article A" can be used as the label of "push object A", and if the feedback effect of "push object B" on "article B" is good, then the keywords in "article B" can be used as the label of "push object B". In this way, all push objects can be labeled by pushing multiple first commodity information, and then the second commodity information is received, and then the target push object is determined based on the second commodity information and the label of the push object, and finally the second commodity information is pushed to the target push object. Compared with the method of labeling the user by searching the user's browsing data, the present invention sends the first commodity information to the user and labels it based on its feedback information, so it does not need to spend time and effort to find the user's browsing data, and the labels attached to the user are more comprehensive, which can deeply develop the user's needs.
[0012] In some embodiments, optionally, before the step of receiving the second product information, it also includes: generating multiple user groups in response to the first input, and determining the group label of each user group; allocating the push object to the corresponding user group based on the label of each push object and the group label of each user group; based on the second product information and the label of the push object, determining the step of target push object, specifically including: determining the first keyword based on the second product information; judging whether the group label of each user group includes the first keyword; determining the user group whose group label includes the first keyword as the target user group; determining the push object under the target user group as the target push object.
[0013] In this embodiment, all users are grouped according to different labels in advance to achieve batch sending of user groups. When sending the second product information, the group label can be directly matched without matching the user labels one by one, and the sending rate is faster. For example, three user groups are established according to brands, namely "Brand A Group", "Brand B Group" and "Brand C Group". In this way, the push objects with the "Brand A" label are assigned to the "Brand A Group", the push objects with the "Brand B" label are assigned to the "Brand B Group", and the push objects with the "Brand C" label are assigned to the "Brand C Group". In this way, when sending information about Brand A cars, it is directly matched to the Brand A group and sent to all push objects under the Brand A group, which makes the push efficiency faster. Among them, the first input can be a group creation instruction given by the user. The user sets which groups need to be established in advance and determines the group label of each group.
[0014] In some embodiments, optionally, the step of determining the target push object based on the second product information and the label of the push object specifically includes: determining the first keyword based on the second product information; judging whether the label of the push object includes the first keyword; and determining that the push object whose label includes the first keyword is the target push object.
[0015] In this embodiment, compared with "group sending", the push objects are checked one by one to ensure accurate matching of the target push objects. For example, in the process of grouping, there are "Brand A Group", "Brand B Group" and "Brand C Group", but the second product information to be sent is about the car of brand D. In this case, group sending is not possible. It is necessary to match the push object with the "Brand D" label from all the push objects so as to push it.
[0016] In some embodiments, optionally, the method for pushing product information further includes: obtaining feedback information of a target push object with respect to the second product information; and updating a tag of the target push object according to the feedback information of the target push object with respect to the second product information.
[0017] In this embodiment, the label of the target push object is adjusted in real time through the feedback information of the target push object for the second product information. Through repeated optimization, the user's transaction rate is higher. The feedback information for the second product information can be, for example, the feedback sentence information, and then the system can extract the keywords in the feedback sentence information to update the label of the target push object. For example, "User A" typed "Brand A cars are better than Brand B cars" in the comment, so the system can extract the corresponding sentence and use "Brand A" as the label of "User A", so that each feedback can improve the user's label, thereby increasing the transaction volume.
[0018] In some embodiments, optionally, before the step of receiving the second product information, it also includes: establishing multiple user groups and determining the labels of the push objects required under each user group; based on the label of each push object, classifying different push objects into corresponding user groups; based on the second product information and the label of the push object, determining the step of the target push object specifically includes: determining the information category of the second product information; based on the correspondence between the preset information category and multiple user groups, determining the push object under the user group corresponding to the second product information as the target push object.
[0019] In this embodiment, different user groups can be created in advance. It can be understood that each user group corresponds to a user level, and the push objects that meet the conditions are classified into the corresponding user groups, which is equivalent to forming user groups of different levels. In this way, when pushing the second product information, the push objects under the user group corresponding to the second product information can be determined as the target push objects according to the correspondence between the preset information categories and multiple user groups. For example, the number of user groups is 5, corresponding to 5 user levels, and the information categories of the second product information are also 5, corresponding to 5 information levels. In this way, the product information of level 1 can be sent to the user group of level 1, thereby achieving accurate delivery for user groups of different levels.
[0020] In some embodiments, optionally, the feedback information for the first product information includes viewing time, and the step of generating a label for the corresponding push object based on the feedback information of each push object for the first product information specifically includes: determining the product keyword based on the first product information; judging whether the viewing time of each push object for the first product information is greater than a preset time; screening out push objects whose viewing time is greater than the preset time; and generating labels for push objects whose viewing time is greater than the preset time based on the product keywords.
[0021] In this technical solution, if the viewing time of "push object A" for "article A" is greater than the preset time, the product keyword in "article A", such as "brand A", can be used as the label of "push object A". The preset time can be greater than or equal to 20 minutes.
[0022] In some embodiments, optionally, the method for pushing product information also includes: obtaining multiple user forms, and determining the field name of each user form and the field data under the corresponding field name; based on all the field names, merging the field data under the field names with the same meaning; based on all the merged field names and the field data under the corresponding field names, generating a total user form; and determining multiple push objects based on the total user form.
[0023] In this technical solution, user forms can be obtained from multiple channels, such as "APP (Application) Software" or surveys, etc. For different user forms, the field data under the field names with the same meaning are merged. For example, "User Name" and "User Name" have the same meaning. At this time, all field data under the "User Name" and "User Name" fields are merged to ensure that data will not be lost. Fields with different meanings are merged, and the matching accuracy is improved by reasonably cleaning the user's data.
[0024] The second aspect of the present invention provides a device for pushing product information, including: a determination unit, used to determine multiple push objects; a push unit, used to push at least one first product information to each push object; an acquisition unit, used to obtain feedback information of each push object for the first product information; a label generation unit, used to generate a label corresponding to the push object based on the feedback information of each push object for the first product information; a receiving unit, used to receive second product information; the determination unit is also used to determine the target push object based on the second product information and the label of the push object; the push unit is also used to push the second product information to the target push object.
[0025] The device for pushing product information of the present invention sends the first product information to the user and labels it based on the feedback information thereof, thereby eliminating the need to waste time and effort in searching for the user's browsing data, and the labels affixed to the user are more comprehensive, thereby enabling in-depth development of the user's needs.
[0026] The third aspect of the present invention provides an electronic device, including a memory and a processor, wherein a computer program or instruction is stored in the memory, and when the processor executes the computer program or instruction, a method for pushing product information provided by any technical solution of the first aspect of the present application is implemented.
[0027] Since the electronic device provided by the present invention can implement the steps of the method for pushing commodity information provided by any technical solution of the first aspect of the present invention, it has all the beneficial effects of the method for pushing commodity information.
[0028] The fourth aspect of the present invention provides a readable storage medium, on which a program or instruction is stored. When a processor executes the program or instruction, a method for pushing commodity information provided by any technical solution of the first aspect of the present application is implemented.
[0029] Since the readable storage medium provided by the present invention can implement the steps of the method for pushing commodity information provided by any technical solution of the first aspect of the present invention, it has all the beneficial effects of the method for pushing commodity information. BRIEF DESCRIPTION OF THE DRAWINGS
[0030] Figure 1 One of the flow diagrams of the method for pushing commodity information provided by an embodiment of the present invention is shown; Figure 2 A second flow chart of a method for pushing product information provided by an embodiment of the present invention is shown; Figure 3 A diagram showing user grouping of a method for pushing product information provided by an embodiment of the present invention; Figure 4 A third flow chart of the method for pushing product information provided by an embodiment of the present invention is shown; Figure 5 A structural block diagram showing a device for pushing commodity information provided by an embodiment of the present invention; Figure 6 A structural block diagram of an electronic device provided by an embodiment of the present invention is shown; Figure 7 One of the software interface diagrams of the method for pushing commodity information provided by an embodiment of the present invention is shown; Fig. 8A A push diagram showing a method for pushing commodity information provided by an embodiment of the present invention; Figure 8B Another part of the push diagram of the method for pushing commodity information provided by the embodiment of the present invention is shown; Fig. 9 A user tag state diagram showing a method for pushing product information provided by an embodiment of the present invention; Fig.10 The second software interface diagram of the method for pushing commodity information provided by the embodiment of the present invention is shown; Fig.11 A label category diagram of a method for pushing commodity information provided by an embodiment of the present invention is shown.
[0031] in, Figure 5 and Figure 6 The corresponding relationship between the reference numerals and component names in the figure is: 1 a device for pushing product information, 12 a determination unit, 14 a pushing unit, 16 an acquisition unit, 18 a label generation unit, 19 a receiving unit, 2 an electronic device, 22 a memory, 24 a processor. DETAILED DESCRIPTION
[0032] In order to more clearly understand the above aspects, features and advantages of the embodiments of the present invention, the embodiments of the present invention are further described in detail below in conjunction with the accompanying drawings and specific implementation methods. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.
[0033] In the following description, many specific details are set forth to facilitate a full understanding of the embodiments according to the present invention. However, the embodiments according to the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the embodiments according to the present invention is not limited to the specific embodiments disclosed below.
[0034] like Figure 1 As shown, this embodiment provides a method for pushing product information, including the following steps: S102: Determine multiple push objects; S104: Push at least one first commodity information to each push object; S106: Obtaining feedback information from each push object regarding the first product information; S108: generating a label corresponding to the push object based on the feedback information of each push object regarding the first product information; S110: receiving second product information; S112: Determine a target push object based on the second product information and the label of the push object; S114: Push the second product information to the target push object.
[0035] The method for pushing commodity information provided in this embodiment first determines multiple push objects, which are users, and pushes at least one first commodity information to each push object. The first commodity information can be an article that has been published, etc., and obtains feedback information of each push object for the first commodity information. In this way, based on the feedback information of each push object for the first commodity information, a label of the corresponding push object can be generated. For example, if the feedback effect of "push object A" on "article A" is good, then the keywords in "article A" can be used as the label of "push object A", and if the feedback effect of "push object B" on "article B" is good, then the keywords in "article B" can be used as the label of "push object B". In this way, through the push of multiple first commodity information, all push objects can be labeled, and then the second commodity information is received, and then the target push object is determined based on the second commodity information and the label of the push object, and finally the second commodity information is pushed to the target push object. Compared with the method of labeling the user by searching the user's browsing data, the present invention sends the first commodity information to the user and labels it based on its feedback information, so there is no need to spend time and effort to find the user's browsing data, and the label attached to the user is more comprehensive, which can deeply develop the user's needs.
[0036] In some embodiments, optionally, before the step of receiving the second product information, it also includes: generating multiple user groups in response to the first input, and determining the group label of each user group; allocating the push object to the corresponding user group based on the label of each push object and the group label of each user group; based on the second product information and the label of the push object, determining the step of target push object, specifically including: determining the first keyword based on the second product information; judging whether the group label of each user group includes the first keyword; determining the user group whose group label includes the first keyword as the target user group; determining the push object under the target user group as the target push object.
[0037] In this embodiment, all users are grouped according to different labels in advance to achieve batch sending of user groups. When sending the second product information, the group label can be directly matched without matching the user labels one by one, and the sending rate is faster. For example, three user groups are established according to brands, namely "Brand A Group", "Brand B Group" and "Brand C Group". In this way, the push objects with the "Brand A" label are assigned to the "Brand A Group", the push objects with the "Brand B" label are assigned to the "Brand B Group", and the push objects with the "Brand C" label are assigned to the "Brand C Group". In this way, when sending information about Brand A cars, it is directly matched to the Brand A group and sent to all push objects under the Brand A group, which makes the push efficiency faster. Among them, the first input can be a group creation instruction given by the user. The user sets which groups need to be established in advance and determines the group label of each group.
[0038] Further, such as Fig. 8A and Figure 8B As shown, users can be divided into customer group A, customer group B and customer group C. The key behavior of customer group A is to browse car models, which means that customer group A pays more attention to car models. The strategy center mainly lies in the system's ability to send different product information to different users through different strategies. For example, content strategies include interactivity and preferentiality, etc. The contact methods include WeChat articles and text messages, etc. Since customer group A pays more attention to car models, articles targeting car models that customer group A pays attention to can be sent to customer group A, thereby promoting the conversion rate of customer group A. In addition, the present invention can also customize different articles according to different customer groups. The present invention divides the push content into three parts: "head", "waist" and "legs". The "head" represents the perceptual content of product interest intentions, such as content, activities or topics, the "waist" represents VR (Virtual Reality) / 360 car viewing, and the "legs" represent online customer service and discount coupons, etc., so as to draw different push content for different customer groups and improve the conversion rate.
[0039] In some embodiments, optionally, the step of determining the target push object based on the second product information and the label of the push object specifically includes: determining the first keyword based on the second product information; judging whether the label of the push object includes the first keyword; and determining that the push object whose label includes the first keyword is the target push object.
[0040] In this embodiment, compared with "group sending", the push objects are checked one by one to ensure accurate matching of the target push objects. For example, in the process of grouping, there are "Brand A Group", "Brand B Group" and "Brand C Group", but the second product information to be sent is about the car of brand D. In this case, group sending is not possible. It is necessary to match the push object with the "Brand D" label from all the push objects so as to push it.
[0041] In some embodiments, optionally, the method for pushing product information further includes: obtaining feedback information of a target push object with respect to the second product information; and updating a tag of the target push object according to the feedback information of the target push object with respect to the second product information.
[0042] In this embodiment, the label of the target push object is adjusted in real time through the feedback information of the target push object on the second product information, and the user's transaction rate is higher through repeated optimization. The feedback information on the second product information can be, for example, feedback sentence information, and then the system can extract keywords in the feedback sentence information to update the label of the target push object.
[0043] For example, if "User A" types in the comment "Brand A's cars are better than Brand B's cars", the system can extract the corresponding sentence and use "Brand A" as the label of "User A". Each feedback can improve the user's label and increase transaction volume.
[0044] In some embodiments, optionally, before the step of receiving the second product information, it also includes: establishing multiple user groups and determining the labels of the push objects required under each user group; based on the label of each push object, classifying different push objects into corresponding user groups; based on the second product information and the label of the push object, determining the step of the target push object specifically includes: determining the information category of the second product information; based on the correspondence between the preset information category and multiple user groups, determining the push object under the user group corresponding to the second product information as the target push object.
[0045] In this embodiment, different user groups can be created in advance, each user group corresponds to a user level, and the push objects that meet the conditions are classified into the corresponding user groups. This is equivalent to forming user groups of different levels. In this way, when pushing the second product information, the push objects under the user group corresponding to the second product information can be determined as the target push objects based on the correspondence between the preset information category and the user group.
[0046] For example, taking Table 1 below as an example, the number of user groups is 8, and the 8 levels of user groups are divided into A+ super high value, A-important maintenance, B+ super high value, B-important maintenance, C+ super high value, C-important maintenance, D+ super high value, and D-important maintenance. In this way, each level of user group has its corresponding population characteristics. In this way, when pushing the second product information, the information category of the second product information can be determined. This process can be the information category input during the user input of the second product information. If the type of the second product information currently to be pushed is A+, then it will be sent to the A+ super high value user group, so that all users in the A+ super high value user group can receive this second product information. This distribution method can send some articles that promote transactions to users of high-quality levels, and some articles that increase user expectations to users with low expectations.
[0047] Table 1
[0048] In addition, the present invention can also modify the user's label and re-group it according to the user's feedback information. For example, for A+ super-high value users, when pushing the second product information of type A+, by obtaining the viewing time of the A+ user, if the viewing time of the A+ user is relatively short, or the pushed A+ type article is not opened, then at this time, the system can modify the user's label "near to store time" to "far to store time", and adjust the user's level from A+ to A-, thereby increasing the user's transaction volume through multiple optimization methods.
[0049] In some embodiments, optionally, the feedback information for the first product information includes viewing time, and the step of generating a label for the corresponding push object based on the feedback information of each push object for the first product information specifically includes: determining the product keyword based on the first product information; judging whether the viewing time of each push object for the first product information is greater than a preset time; screening out push objects whose viewing time is greater than the preset time; and generating labels for push objects whose viewing time is greater than the preset time based on the product keywords.
[0050] In this technical solution, if the viewing time of "push object A" for "article A" is greater than the preset time, the product keyword in "article A", such as "brand A", can be used as the label of "push object A". The preset time can be greater than or equal to 20 minutes.
[0051] In the process of labeling the push object, the user's label status diagram is as follows: Fig. 9 As shown, the label categories are Fig.11 As shown in Table 2: Table 2
[0052] Furthermore, the corresponding relationship between each tag and its attribute value, update cycle, update rule, etc. is shown in Tables 3 to 6 below: Table 3
[0053] Table 4
[0054] Table 5
[0055] Table 6
[0056] In addition, each tag also involves tag generation conditions and application scenarios.
[0057] In some embodiments, optionally, the method for pushing product information also includes: obtaining multiple user forms, and determining the field name of each user form and the field data under the corresponding field name; based on all the field names, merging the field data under the field names with the same meaning; based on all the merged field names and the field data under the corresponding field names, generating a total user form; and determining multiple push objects based on the total user form.
[0058] In this technical solution, user forms can be obtained from multiple channels, such as "APP software" or surveys, etc. For different user forms, the field data under the field names with the same meaning are merged. For example, "user name" and "user name" have the same meaning. At this time, all field data under the "user name" and "user name" fields are merged to ensure that data will not be lost. Fields with different meanings are merged, and the user's data is reasonably cleaned to improve the matching accuracy.
[0059] Next, the applicant analyzes the method for pushing product information of the present invention from another perspective, which is mainly to solve the following problems: How to reasonably clean the existing user data in the business system to achieve classified trial? How to produce targeted content for different classified policyholder groups? In what way and frequency to care for policyholders? like Figure 2 As shown, the method for pushing product information includes the following steps: S202: Collect user data; S204: Verify whether the data is complete; if so, execute S208; if not, execute S206; S206: remind the salesperson to complete the data; S208: Determine the cleaned user pool; S210: All staff members push the content in the content pool; S212: Establish a tag pool based on user feedback; S214: Pushing content according to matching rules; S216: Push content according to marketing rules; S218: Optimize matching rules and marketing rules.
[0060] The method for pushing product information in this embodiment first collects user data and verifies whether the data is complete. If it is incomplete, the salesperson is reminded to complete the data. If the data is complete, a cleaned user pool is obtained, and then all employees push the content in the content pool in the first round. The first round of push is mainly to label different users with different tags. In this way, after the tag pool is established based on user feedback, since each user has its corresponding tag, when the second round of push is carried out, the content can be pushed according to the matching rules or marketing rules. For example, articles about brand A cars are pushed to users with brand A tags, or A-level articles are pushed to A-level users, and so on. Finally, the matching rules and marketing rules can be optimized according to user feedback.
[0061] In addition, the present invention can also group users according to their tags. Taking the insurance business as an example, according to the needs of the insurance business, all users need to be divided into four user groups: new transfer, under repair but not under insurance, direct to the store, and neither repair nor under insurance. Figure 3 As shown, for the new renewal group, the user's belonging stickiness can be increased when pushing articles. For the user group that is under repair but not under warranty, the after-sales insurance customer user group can be used as the basis to simply and crudely provide the user with the most interesting price and rights marketing plan to maximize the conversion rate of this group of people. For the people who come directly to the store, the user's renewal follow-up status and other label portraits can be systematically understood, so as to achieve more accurate sales conversion. For the group that is not under repair or warranty, in addition to traditional telephone recalls, the membership system and the rights of old users to attract new users can also be used to activate users through seed users, so as to adopt different marketing strategies according to different types of users.
[0062] In addition, the present invention also proposes a process of determining labels by a factor algorithm, as shown in Table 7 below: Table 7
[0063] In this step, users can set multiple factors for the label according to their needs. For example, the label "Accumulated maintenance frequency in the store" in Table 7 includes three influencing factors, namely "out of warranty", "4S distance" and "replacement on time". In the specific calculation process, the influence value of each influencing factor is determined in turn. Taking "out of warranty" as an example, the calculation process of the influence value of the influencing factor is to first determine whether the policyholder's vehicle is an unwarranted vehicle or an out of warranty vehicle. If the policyholder's vehicle is an unwarranted vehicle and the number of maintenances within 3 years of purchase is 6, then the influencing factor "out of warranty" is 0. The influence value of the sub-item is 6 times × 70% (weight) = 4.2 times. Similarly, the influence values of the influencing factors of "4S distance" and "replacement on time" are calculated. Finally, the influence values of all influencing factors are classified and summed to get the total influence value, which is the label value of the label "cumulative frequency of maintenance visits to stores". In actual application, the label values can be divided into multiple levels according to specific needs, such as high and low levels. In this way, in the later stage, the policyholders with a high cumulative frequency of maintenance visits to stores or a low cumulative frequency of maintenance visits to stores can be quickly screened out, so as to push different types of articles.
[0064] In addition, it should be made clear that the default is that the owner is a new owner for 0-3 years, the default is that the owner is an old owner for 3-6 years, and the default is that after 6 years, the owner is a potential second-hand owner. The default is that the maintenance and replacement of parts are done once every 4 years. The default single maintenance price is: 300 for minor maintenance and 600 for major maintenance. The default single oil change price is: 150; the default replacement of premium parts is: 100 for minor maintenance and 300 for major maintenance. The default consumption limit for public vehicles is 30% higher than that for private vehicles. Among them, factors and weights need to be updated regularly when setting in the CRM system / manually.
[0065] like Figure 4 As shown, the present invention can divide users into four groups, namely user group A, user group B, user group C, user group D and user group E, and then the system can perform the following operations: S402: Online invitation; S404: Determine whether the user accepts the arrangement to go to the store, if yes, execute S406, if no, execute S408; S406: invite to the store; then transfer to S412; S408: Gifting rights; S410: Determine whether the user accepts the arrangement to go to the store, if yes, execute S406, if no, execute S418; S412: Reception and ordering; S414: Pick up the car and leave the store; S416: Satisfaction evaluation; transfer to S420; S418: Determine that the user arrives at the store on his own; S420: Determine whether the user is willing to make an evaluation; if yes, go to S422; if no, go to S424; S422: Update the label according to the evaluation; S424: Conduct the next round of invitations.
[0066] The present invention can divide users into five groups, namely user group A, user group B, user group C, user group D and user group E. Then the system can make an online invitation to see whether the user accepts to be arranged to the store. If the user accepts, then the user is directly invited to the store. If the user does not accept, the benefits can be given, and then it is checked again whether the user accepts to be arranged to the store. If the user accepts, then the user is directly invited to the store, and then the order is received and the user picks up the car and leaves the store. Then the satisfaction evaluation is carried out and the evaluation is carried out in time. If the user is willing to evaluate, the label of the user group is updated according to the evaluation. If the customer is unwilling to evaluate, the process ends. If the user still does not accept to be arranged to the store, then the user needs to go to the store by himself. The software interface of this process is shown in the figure below Fig.10 shown.
[0067] In the actual application process of the push method of the present invention, Figure 7 As shown, it mainly includes six major sections: event operation, user operation, community operation, product operation, channel operation and data-driven. Each section includes multiple functions. By realizing each function, the user conversion rate can be greatly improved.
[0068] The difference between the push method of the present invention and the conventional push method is that: Difference 1: The existing base is not classified or grouped, and marketing promotion is carried out through simple basic information (mobile phone number, vehicle VIN (Vehicle Identification Number)), etc.; after the new technology classifies and groups the base, the common points can be unified and mechanically promoted in batches to reduce the actual marketing cost, and the differences can be targeted and personalized to each individual to maximize the conversion rate.
[0069] Difference 2: Existing marketing pushes are all one-time promotions and one-time collection of marketing effects. There is no sustainable and traceable rule source. Good marketing effects cannot be replicated and bad marketing effects cannot be analyzed. New technologies use tags as the traceability rule source to analyze the good and bad marketing effects in depth to the rationality of tag matching, continuously optimize matching rules, and thus flexibly change the objects and content of the next round of marketing pushes.
[0070] Difference three: The existing operating rules for policyholders are relatively simple, the cost of changing the rules is very high, and there is no way to analyze how decisions can be changed; the new technology uses AI algorithms to efficiently match large amounts of raw data to algorithm models, thereby reducing the time cost of rule-making, improving the rationality of new rules, and adding a variety of marketing rules to facilitate new marketing attempts.
[0071] like Figure 5 As shown, the second aspect of the present invention provides a device 1 for pushing product information, including: a determination unit 12, used to determine multiple push objects; a push unit 14, used to push at least one first product information to each push object; an acquisition unit 16, used to obtain feedback information of each push object for the first product information; a label generation unit 18, used to generate a label corresponding to the push object based on the feedback information of each push object for the first product information; a receiving unit 19, used to receive the second product information; the determination unit 12 is also used to determine the target push object based on the second product information and the label of the push object; the push unit 14 is also used to push the second product information to the target push object.
[0072] like Figure 6 As shown, the third aspect of the present invention provides an electronic device 2, including a memory 22 and a processor 24, wherein the memory 22 stores a computer program or instruction, and when the processor 24 executes the computer program or instruction, a method for pushing product information provided by any technical solution of the first aspect of the present application is implemented.
[0073] The fourth aspect of the present invention provides a readable storage medium, on which a program or instruction is stored. When a processor executes the program or instruction, a method for pushing commodity information provided by any technical solution of the first aspect of the present application is implemented.
[0074] Since the readable storage medium provided by the present invention can implement the steps of the method for pushing commodity information provided by any technical solution of the first aspect of the present invention, it has all the beneficial effects of the method for pushing commodity information.
[0075] In the embodiments according to the present invention, the terms "first", "second", and "third" are only used for description and cannot be understood as indicating or implying relative importance; the term "plurality" refers to two or more, unless otherwise clearly defined. The terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense. For example, "connected" can be a fixed connection, a detachable connection, or an integral connection; "connected" can be a direct connection or an indirect connection through an intermediate medium. For those of ordinary skill in the art, the specific meanings of the above terms in the embodiments according to the present invention can be understood according to specific circumstances.
[0076] In addition, although each operation is described in a specific order, this should be understood as requiring such operation to be performed in a specific order or in a sequential order, or requiring that all illustrated operations should be performed to obtain desired results. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present invention. Some features described in the context of a separate embodiment can also be implemented in a single implementation in combination. On the contrary, the various features described in the context of a single implementation can also be implemented in multiple implementations individually or in any suitable sub-combination mode.
[0077] Although the subject matter has been described in the language of specific structural features and / or method logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. On the contrary, the specific features and actions described above are merely example forms of implementing the claims.
[0078] The above are only preferred embodiments according to the embodiments of the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, various modifications and changes may be made according to the embodiments of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the embodiments of the present invention shall be included in the protection scope of the embodiments of the present invention.
Claims
1. A method for pushing commodity information, characterized in that: include: Determine multiple push targets; Pushing at least one first commodity information to each of the push objects; Obtaining feedback information from each push object regarding the first product information; generating a label corresponding to the push object based on feedback information of each push object regarding the first product information; receiving second product information; Determine a target push object based on the second product information and the label of the push object; The second product information is pushed to the target push object.
2. The method for pushing commodity information according to claim 1, characterized in that: Before the step of receiving the second product information, the method further includes: In response to the first input, generating a plurality of user groups and determining a group label for each of the user groups; Based on the label of each of the push objects and the group label of each of the user groups, the push objects are allocated to corresponding user groups; The step of determining the target push object based on the second product information and the label of the push object specifically includes: Determining a first keyword based on the second product information; Determining whether the group tag of each of the user groups includes the first keyword; Determine a user group whose group tag includes the first keyword as a target user group; The push objects under the target user group are determined as the target push objects.
3. The method for pushing commodity information according to claim 1, characterized in that: The step of determining the target push object based on the second product information and the label of the push object specifically includes: Determining a first keyword based on the second product information; Determining whether the tag of the push object includes the first keyword; A push object whose tag includes the first keyword is determined as the target push object.
4. The method for pushing commodity information according to claim 1, characterized in that: Also includes: Obtaining feedback information from the target push object regarding the second product information; The tag of the target push object is updated according to the feedback information of the target push object regarding the second product information.
5. The method for pushing commodity information according to claim 1, characterized in that: Before the step of receiving the second product information, the method further includes: Create multiple user groups and determine the labels of the push objects required for each user group; Based on the label of each push object, classify different push objects into corresponding user groups; The step of determining the target push object based on the second product information and the label of the push object specifically includes: determining the information category of the second product information; Based on the correspondence between the preset information categories and the plurality of user groups, the push objects under the user group corresponding to the second product information are determined as the target push objects.
6. The method for pushing commodity information according to claim 1, characterized in that: The feedback information for the first product information includes viewing time, and the step of generating a label corresponding to the push object based on the feedback information of each push object for the first product information specifically includes: Determining product keywords based on the first product information; Determine whether the viewing time of each push object for the first product information is greater than a preset time; Filter out the push recipients whose viewing time is longer than the preset time; Based on the commodity keywords, a label of a push object whose viewing time is greater than a preset time is generated.
7. The method for pushing commodity information according to claim 1, characterized in that: Also includes: Acquire multiple user forms, and determine the field name of each user form and the field data under the corresponding field name; Based on all the field names, the field data under the field names with the same meaning are merged; Generate a total user form based on all merged field names and field data under the corresponding field names; A plurality of push objects are determined based on the total user form.
8. A device for pushing commodity information, characterized in that: include: A determination unit, used for determining multiple push objects; A push unit, used to push at least one first commodity information to each of the push objects; An acquiring unit, configured to acquire feedback information of each push object with respect to the first product information; a label generating unit, configured to generate a label corresponding to a push object based on feedback information of each push object regarding the first commodity information; A receiving unit, configured to receive second commodity information; The determining unit is further configured to determine a target push object based on the second commodity information and the label of the push object; The push unit is further used to push the second product information to the target push object.
9. An electronic device, characterized in that: include: A memory and a processor, wherein the memory stores a computer program or an instruction, and the processor implements the method for pushing commodity information according to any one of claims 1 to 7 when executing the computer program or the instruction.
10. A readable storage medium, characterized in that: The readable storage medium stores a program or an instruction, and when the processor executes the program or the instruction, the method for pushing commodity information according to any one of claims 1 to 7 is implemented.
